2 files changed, 61 insertions, 0 deletions
diff --git a/test-files/sample.rtf b/test-files/sample.rtf
new file mode 100644
index 0000000..7120f8f
--- /dev/null
+++ b/test-files/sample.rtf
@@ -0,0 +1,60 @@
+{\rtf1\ansi\ansicpg1252\uc1\deff0\stshfdbch0\stshfloch0\stshfhich0\stshfbi0\deflang1033\deflangfe1033{\fonttbl{\f0\froman\fcharset0\fprq2{\*\panose 02020603050405020304}Times New Roman;}{\f1\fswiss\fcharset0\fprq2{\*\panose 020b0604020202020204}Arial;}
+{\f2\fmodern\fcharset0\fprq1{\*\panose 02070309020205020404}Courier New;}{\f3\froman\fcharset2\fprq2{\*\panose 05050102010706020507}Symbol;}{\f10\fnil\fcharset2\fprq2{\*\panose 05000000000000000000}Wingdings;}
+{\f119\froman\fcharset238\fprq2 Times New Roman CE;}{\f120\froman\fcharset204\fprq2 Times New Roman Cyr;}{\f122\froman\fcharset161\fprq2 Times New Roman Greek;}{\f123\froman\fcharset162\fprq2 Times New Roman Tur;}
+{\f124\froman\fcharset177\fprq2 Times New Roman (Hebrew);}{\f125\froman\fcharset178\fprq2 Times New Roman (Arabic);}{\f126\froman\fcharset186\fprq2 Times New Roman Baltic;}{\f127\froman\fcharset163\fprq2 Times New Roman (Vietnamese);}
+{\f129\fswiss\fcharset238\fprq2 Arial CE;}{\f130\fswiss\fcharset204\fprq2 Arial Cyr;}{\f132\fswiss\fcharset161\fprq2 Arial Greek;}{\f133\fswiss\fcharset162\fprq2 Arial Tur;}{\f134\fswiss\fcharset177\fprq2 Arial (Hebrew);}
+{\f135\fswiss\fcharset178\fprq2 Arial (Arabic);}{\f136\fswiss\fcharset186\fprq2 Arial Baltic;}{\f137\fswiss\fcharset163\fprq2 Arial (Vietnamese);}{\f139\fmodern\fcharset238\fprq1 Courier New CE;}{\f140\fmodern\fcharset204\fprq1 Courier New Cyr;}
+{\f142\fmodern\fcharset161\fprq1 Courier New Greek;}{\f143\fmodern\fcharset162\fprq1 Courier New Tur;}{\f144\fmodern\fcharset177\fprq1 Courier New (Hebrew);}{\f145\fmodern\fcharset178\fprq1 Courier New (Arabic);}
+{\f146\fmodern\fcharset186\fprq1 Courier New Baltic;}{\f147\fmodern\fcharset163\fprq1 Courier New (Vietnamese);}}{\colortbl;\red0\green0\blue0;\red0\green0\blue255;\red0\green255\blue255;\red0\green255\blue0;\red255\green0\blue255;\red255\green0\blue0;
+\red255\green255\blue0;\red255\green255\blue255;\red0\green0\blue128;\red0\green128\blue128;\red0\green128\blue0;\red128\green0\blue128;\red128\green0\blue0;\red128\green128\blue0;\red128\green128\blue128;\red192\green192\blue192;}{\stylesheet{
+\ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0 \fs24\lang1033\langfe1033\cgrid\langnp1033\langfenp1033 \snext0 Normal;}{\s1\ql \li0\ri0\sb240\sa60\keepn\widctlpar\aspalpha\aspnum\faauto\outlinelevel0\adjustright\rin0\lin0\itap0 
+\b\f1\fs32\lang1033\langfe1033\kerning32\cgrid\langnp1033\langfenp1033 \sbasedon0 \snext0 \styrsid2294299 heading 1;}{\*\cs10 \additive \ssemihidden Default Paragraph Font;}{\*
+\ts11\tsrowd\trftsWidthB3\trpaddl108\trpaddr108\trpaddfl3\trpaddft3\trpaddfb3\trpaddfr3\tscellwidthfts0\tsvertalt\tsbrdrt\tsbrdrl\tsbrdrb\tsbrdrr\tsbrdrdgl\tsbrdrdgr\tsbrdrh\tsbrdrv 
+\ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0 \fs20\lang1024\langfe1024\cgrid\langnp1024\langfenp1024 \snext11 \ssemihidden Normal Table;}{\*\ts15\tsrowd\trbrdrt\brdrs\brdrw10 \trbrdrl\brdrs\brdrw10 \trbrdrb\brdrs\brdrw10 
+\trbrdrr\brdrs\brdrw10 \trbrdrh\brdrs\brdrw10 \trbrdrv\brdrs\brdrw10 \trftsWidthB3\trpaddl108\trpaddr108\trpaddfl3\trpaddft3\trpaddfb3\trpaddfr3\tscellwidthfts0\tsvertalt\tsbrdrt\tsbrdrl\tsbrdrb\tsbrdrr\tsbrdrdgl\tsbrdrdgr\tsbrdrh\tsbrdrv 
+\ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0 \fs20\lang1024\langfe1024\cgrid\langnp1024\langfenp1024 \sbasedon11 \snext15 \styrsid2294299 Table Grid;}}{\*\latentstyles\lsdstimax156\lsdlockeddef0}{\*\listtable
+{\list\listtemplateid-767292450\listhybrid{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext\leveltemplateid67698689\'01\u-3913 ?;}{\levelnumbers;}\f3\fbias0 \fi-360\li720
+\jclisttab\tx720\lin720 }{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext\leveltemplateid67698691\'01o;}{\levelnumbers;}\f2\fbias0 \fi-360\li1440\jclisttab\tx1440\lin1440 }{\listlevel
+\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext\leveltemplateid67698693\'01\u-3929 ?;}{\levelnumbers;}\f10\fbias0 \fi-360\li2160\jclisttab\tx2160\lin2160 }{\listlevel\levelnfc23\levelnfcn23
+\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext\leveltemplateid67698689\'01\u-3913 ?;}{\levelnumbers;}\f3\fbias0 \fi-360\li2880\jclisttab\tx2880\lin2880 }{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0
+\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext\leveltemplateid67698691\'01o;}{\levelnumbers;}\f2\fbias0 \fi-360\li3600\jclisttab\tx3600\lin3600 }{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1
+\levelspace360\levelindent0{\leveltext\leveltemplateid67698693\'01\u-3929 ?;}{\levelnumbers;}\f10\fbias0 \fi-360\li4320\jclisttab\tx4320\lin4320 }{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0
+{\leveltext\leveltemplateid67698689\'01\u-3913 ?;}{\levelnumbers;}\f3\fbias0 \fi-360\li5040\jclisttab\tx5040\lin5040 }{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext
+\leveltemplateid67698691\'01o;}{\levelnumbers;}\f2\fbias0 \fi-360\li5760\jclisttab\tx5760\lin5760 }{\listlevel\levelnfc23\levelnfcn23\leveljc0\leveljcn0\levelfollow0\levelstartat1\levelspace360\levelindent0{\leveltext\leveltemplateid67698693
+\'01\u-3929 ?;}{\levelnumbers;}\f10\fbias0 \fi-360\li6480\jclisttab\tx6480\lin6480 }{\listname ;}\listid687222349}}{\*\listoverridetable{\listoverride\listid687222349\listoverridecount0\ls1}}{\*\rsidtbl \rsid2294299}{\*\generator Microsoft Word 11.
+0.6113;}{\info{\title This is a test RTF}{\author Nate}{\operator Nate}{\creatim\yr2004\mo3\dy31\hr18\min34}{\revtim\yr2004\mo3\dy31\hr18\min37}{\version1}{\edmins3}{\nofpages2}{\nofwords58}{\nofchars334}{\*\company None}{\nofcharsws391}{\vern24699}}
+\widowctrl\ftnbj\aenddoc\noxlattoyen\expshrtn\noultrlspc\dntblnsbdb\nospaceforul\formshade\horzdoc\dgmargin\dghspace180\dgvspace180\dghorigin1800\dgvorigin1440\dghshow1\dgvshow1
+\jexpand\viewkind1\viewscale80\pgbrdrhead\pgbrdrfoot\splytwnine\ftnlytwnine\htmautsp\nolnhtadjtbl\useltbaln\alntblind\lytcalctblwd\lyttblrtgr\lnbrkrule\nobrkwrptbl\snaptogridincell\allowfieldendsel\wrppunct
+\asianbrkrule\rsidroot2294299\newtblstyruls\nogrowautofit \fet0\sectd \linex0\endnhere\sectlinegrid360\sectdefaultcl\sftnbj {\*\pnseclvl1\pnucrm\pnstart1\pnindent720\pnhang {\pntxta .}}{\*\pnseclvl2\pnucltr\pnstart1\pnindent720\pnhang {\pntxta .}}
+{\*\pnseclvl3\pndec\pnstart1\pnindent720\pnhang {\pntxta .}}{\*\pnseclvl4\pnlcltr\pnstart1\pnindent720\pnhang {\pntxta )}}{\*\pnseclvl5\pndec\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}{\*\pnseclvl6\pnlcltr\pnstart1\pnindent720\pnhang {\pntxtb (}
+{\pntxta )}}{\*\pnseclvl7\pnlcrm\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}{\*\pnseclvl8\pnlcltr\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}{\*\pnseclvl9\pnlcrm\pnstart1\pnindent720\pnhang {\pntxtb (}{\pntxta )}}\pard\plain 
+\s1\ql \li0\ri0\sb240\sa60\keepn\widctlpar\aspalpha\aspnum\faauto\outlinelevel0\adjustright\rin0\lin0\itap0\pararsid2294299 \b\f1\fs32\lang1033\langfe1033\kerning32\cgrid\langnp1033\langfenp1033 {\insrsid2294299 This is a test RTF
+\par }\pard\plain \ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0\pararsid2294299 \fs24\lang1033\langfe1033\cgrid\langnp1033\langfenp1033 {\insrsid2294299 Hi! I\rquote m a test file. This is some }{\b\insrsid2294299 bold}{
+\insrsid2294299  text, and some }{\i\insrsid2294299 italic}{\insrsid2294299  text, as well as some }{\ul\insrsid2294299 underline}{\insrsid2294299  text. And a bit of }{\v\insrsid2294299\charrsid2294299 hidden}{\insrsid2294299  text. So we\rquote 
+re going to end this paragraph here and go on to a nice little list:
+\par 
+\par {\listtext\pard\plain\f3\insrsid2294299 \loch\af3\dbch\af0\hich\f3 \'b7\tab}}\pard \ql \fi-360\li720\ri0\widctlpar\jclisttab\tx720\aspalpha\aspnum\faauto\ls1\adjustright\rin0\lin720\itap0\pararsid2294299 {\insrsid2294299 Item 1
+\par {\listtext\pard\plain\f3\insrsid2294299 \loch\af3\dbch\af0\hich\f3 \'b7\tab}Item 2
+\par {\listtext\pard\plain\f3\insrsid2294299 \loch\af3\dbch\af0\hich\f3 \'b7\tab}Item 3
+\par {\listtext\pard\plain\f3\insrsid2294299 \loch\af3\dbch\af0\hich\f3 \'b7\tab}Item 4
+\par }\pard \ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0\pararsid2294299 {\insrsid2294299 
+\par And now comes a fun table:
+\par 
+\par }\trowd \irow0\irowband0\ts15\trgaph108\trleft-108\trbrdrt\brdrs\brdrw10 \trbrdrl\brdrs\brdrw10 \trbrdrb\brdrs\brdrw10 \trbrdrr\brdrs\brdrw10 \trbrdrh\brdrs\brdrw10 \trbrdrv\brdrs\brdrw10 
+\trftsWidth1\trftsWidthB3\trautofit1\trpaddl108\trpaddr108\trpaddfl3\trpaddft3\trpaddfb3\trpaddfr3\tblrsid2294299\tbllkhdrrows\tbllklastrow\tbllkhdrcols\tbllklastcol \clvertalt\clbrdrt\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr
+\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx2844\clvertalt\clbrdrt\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx5796\clvertalt\clbrdrt
+\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx8748\pard \ql \li0\ri0\widctlpar\intbl\aspalpha\aspnum\faauto\adjustright\rin0\lin0\pararsid2294299 {\insrsid2294299 
+Cell 1\cell Cell 2
+\par More in cell 2\cell Cell 3\cell }\pard \ql \li0\ri0\widctlpar\intbl\aspalpha\aspnum\faauto\adjustright\rin0\lin0 {\insrsid2294299 \trowd \irow0\irowband0\ts15\trgaph108\trleft-108\trbrdrt\brdrs\brdrw10 \trbrdrl\brdrs\brdrw10 \trbrdrb\brdrs\brdrw10 
+\trbrdrr\brdrs\brdrw10 \trbrdrh\brdrs\brdrw10 \trbrdrv\brdrs\brdrw10 \trftsWidth1\trftsWidthB3\trautofit1\trpaddl108\trpaddr108\trpaddfl3\trpaddft3\trpaddfb3\trpaddfr3\tblrsid2294299\tbllkhdrrows\tbllklastrow\tbllkhdrcols\tbllklastcol \clvertalt\clbrdrt
+\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx2844\clvertalt\clbrdrt\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 
+\cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx5796\clvertalt\clbrdrt\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx8748\row }\pard 
+\ql \li0\ri0\widctlpar\intbl\aspalpha\aspnum\faauto\adjustright\rin0\lin0\pararsid2294299 {\insrsid2294299 Next row\cell Next row \cell Next row\cell }\pard \ql \li0\ri0\widctlpar\intbl\aspalpha\aspnum\faauto\adjustright\rin0\lin0 {\insrsid2294299 
+\trowd \irow1\irowband1\lastrow \ts15\trgaph108\trleft-108\trbrdrt\brdrs\brdrw10 \trbrdrl\brdrs\brdrw10 \trbrdrb\brdrs\brdrw10 \trbrdrr\brdrs\brdrw10 \trbrdrh\brdrs\brdrw10 \trbrdrv\brdrs\brdrw10 
+\trftsWidth1\trftsWidthB3\trautofit1\trpaddl108\trpaddr108\trpaddfl3\trpaddft3\trpaddfb3\trpaddfr3\tblrsid2294299\tbllkhdrrows\tbllklastrow\tbllkhdrcols\tbllklastcol \clvertalt\clbrdrt\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr
+\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx2844\clvertalt\clbrdrt\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx5796\clvertalt\clbrdrt
+\brdrs\brdrw10 \clbrdrl\brdrs\brdrw10 \clbrdrb\brdrs\brdrw10 \clbrdrr\brdrs\brdrw10 \cltxlrtb\clftsWidth3\clwWidth2952\clshdrawnil \cellx8748\row }\pard \ql \li0\ri0\widctlpar\aspalpha\aspnum\faauto\adjustright\rin0\lin0\itap0\pararsid2294299 {
+\insrsid2294299 
+\par A page break:
+\par \page And here we\rquote re on the next page.}{\insrsid2294299\charrsid2294299 
+\par }}
+\ No newline at end of file
diff --git a/test-files/sample.xml b/test-files/sample.xml
new file mode 100644
index 0000000..c03cc1f
--- /dev/null
+++ b/test-files/sample.xml
@@ -0,0 +1 @@
+<?xml version="1.0" encoding="UTF-8"?><document><stylesheet><style name="Normal"/><style name="heading 1" bold="1"/></stylesheet><info><title>This is a test RTF</title><author>Nate</author><operator>Nate</operator></info><para style="heading 1"><b>This is a test RTF</b></para><para>Hi! I’m a test file. This is some <b>bold</b> text, and some <i>italic</i> text, as well as some <u>underline</u> text. And a bit of <hide>hidden</hide> text. So we’re going to end this paragraph here and go on to a nice little list:</para><para/><list type="disc" ordered="0" start="1"><para>Item 1</para><para>Item 2</para><para>Item 3</para><para>Item 4</para></list><para/><para>And now comes a fun table:</para><para/><table><row><cell><para>Cell 1</para></cell><cell><para>Cell 2</para><para>More in cell 2</para></cell><cell><para>Cell 3</para></cell></row><row><cell><para>Next row</para></cell><cell><para>Next row </para></cell><cell><para>Next row</para></cell></row></table><para/><para>A page break:</para><page/><para>And here we’re on the next page.</para><para/></document>
+\ No newline at end of file